My bookmarks (as well as, wishlist and advice) for free (for most parts -- some may be non-free) machine learning resources on the web -- personally biased.
- Machine Learning / Deep Learning
- Computer Vision
- Natural Language Processing / Understanding
- Math / Stat / Foundations
- Computer Science
- System Design
- Useful Resources
- Books
- Articles / Blogs / Talks
- [ML] Stanford CS229 Fall 2018 by Andrew Ng
- [ML] Learning from Data by Abu Mostafa, Caltech
- [ML] Foundations of Data Science, Microsoft Research (YouTube)
- [ML] Mining Massive Datasets
- [ML] Cornell CS5787: Applied Machine Learning, Fall 2020 (YouTube)
- [ML] Machine Learning by Google Developer
- [ML] Tom Michell's courses
- Machine Learning 10-601 @CMU in Spring 2015 by Mitchell and Balcan with video (http://www.cs.cmu.edu/~ninamf/courses/601sp15/)
- Tom Mitchell's university page (http://www.cs.cmu.edu/~tom/)
- Maria-Florina Balcan's university page (http://www.cs.cmu.edu/~ninamf/)
- [ML] Harvard CS181: Machine Learning (https://harvard-ml-courses.github.io/cs181-web/)
- [ML] Machine Learning Crash Course by Google (https://developers.google.com/machine-learning/crash-course)
- [ML.Prob] Probabilistic Machine Learning - Philipp Hennig, 2021, Uni-Tuebingen (YouTube)
- [ML] Scalable Machine Learning by Alex Smola at Berkeley in 2012
- [MLD] Full Stack Deep Learning
- [DL] MIT 6.S191 Introduction to Deep Learning (Spring 2021)
- [DL] Deep Learning by Fast.ai
- [DL] UC Berkeley CS182 Spring 2021: Deep Learning on YouTube
- [DL] NYU DS-GA 1008 Deep Learning by LeCun and Canziani
- [DL] T81 558: Applications of Deep Neural Networks by Jeff Heaton, Washington University at St Louis
- [DL] Deep Learning Crash Course 2021 by Alex Smola
- [DL] Deep Learning Course by Fleuret at UNIGE/EPFL with Pytorch (https://fleuret.org/dlc/)
- [DL] UVA Deep Learning Course (https://uvadlc.github.io/)
- YouTube Playlist - UVA Deep Learning Lectures 2020
- YouTube Playlist - Tutorial Notebooks
- GitHub Repo for Jupyter Notebooks (https://github.com/phlippe/uvadlc_notebooks) includes GNN
- Website for Jupyter Notebooks (https://uvadlc-notebooks.readthedocs.io/en/latest/) includes GNN
- [DL.UL] Berkeley CS294-158-SP20: Deep Unsupervised Learning (Spring 2020)
- [ML.GNN] Stanford CS224W: Machine Learning with Graphs (https://cs224w.stanford.edu)
- [DL.GDL/GNN] AMMI 2021 GDL100 Geometric Deep Learning Course (https://geometricdeeplearning.com/lectures/)
- [RL.DL] (2020-Fall) UC Berkeley CS285: Deep Reinforcement Learning (YouTube)
- [CV] Introduction to Computer Vision | Georgia Tech CS 4476 Fall 2019 edition (https://dellaert.github.io/19F-4476/schedule.html)
- [CV.DL] (2020-Fall) UMich EECS 498-007 / 598-005: Deep Learning for Computer Vision (YouTube)
- [ML.GNN] Stanford CS224W: Machine Learning with Graphs (https://cs224w.stanford.edu)
- [DL.GDL/GNN] AMMI 2021 GDL100 Geometric Deep Learning Course (https://geometricdeeplearning.com/lectures/)
- [RL.DL] (2020-Fall) UC Berkeley CS285: Deep Reinforcement Learning (YouTube)
- [NLP.DL] (YouTube) Stanford CS224N: Natural Language Processing with Deep Learning
- [NLP.DL] (YouTube) CMU CS11-747: Neural Nets for NLP 2021
- [NLP.DL] (2020-Fall) CMU CS11-737: Multilingual NLP (YouTube)
- [NLP.DL] (YouTube) UMass CS685: Advanced NLP, Fall 2020
- [Advice] Data Science Career Advice of College Students (https://www.springboard.com/blog/data-scientist-training-college/)
- [DS.ML] 52 Week Curriculum for Data Science in 2021 by Terrence Shin
- [Stat] StatQuest (https://statquest.org/video-index/)
- [Math] Mathematics for Machine Learning (https://mml-book.github.io/)
- [Math.DS.ML] Great contents from 3Blue1Brown on YouTube
- [LinAlg] Linear Algebra Video Lectures by Strang at MIT in 2010 (https://ocw.mit.edu/courses/mathematics/18-06-linear-algebra-spring-2010/video-lectures/)
- [LinAlg] Computational Linear Algebra for Coders (https://github.com/fastai/numerical-linear-algebra) (YouTube)
- [DS.ML] Python Data Science Handbook (https://jakevdp.github.io/PythonDataScienceHandbook/)
- [PhD] Do I Need to Go to University? (http://colah.github.io/posts/2020-05-University/)
- [PhD] A Survival Guide to a PhD (http://karpathy.github.io/2016/09/07/phd/)
- [ML] Probabilistic Programming and Bayesian Methods for Hackers by Davidson-Pilon (with PyMC3 and TFP)
- [ML] Introduction to Statistical Learning (ISLR) by James, Witten, Hastie and Tibshirani (https://www.statlearning.com/)
- [DS] Data Science @OSSU (https://github.com/ossu/data-science)
- [CS] Computer Science @OSSU (https://github.com/ossu/computer-science)
- [Prob.Stat] Seeing Theory: A Visual Introduction to Probability and Statistics (https://seeing-theory.brown.edu/)
- [ML] (2018-Fall) Staford CS229: Machine Learning by Andrew Ng (YouTube)
- [Git] Git from the Bottom up (https://jwiegley.github.io/git-from-the-bottom-up/)
- [CS.Prog] Stanford CS106B: Programming Abstractions in C++ (Course, SEE, YouTube)
- [CS.Prog] Stanford CS106X: Programming Abstractoins in C++ (Accelerated) (Course, YouTube)
- [CS.Sys] Stanford CS107: Computer Organization and Systems (C) (Course, YouTube)
- [CS.Sys] Stanford CS108: Object-Oriented Systems Design (Course)
- [CS.Sys] Stanford CS110: Principles of Computer Systems (Course, YouTube)
- [CS.Network] Stanford CS144: Introduction to Computer Networking (Course, YouTube)
- [CS.Sys] Stanford CS212: Operating Systems and Systems Programming (Course)
- [CS.Web] Stanford CS142: Web Applications (Course)
- [CS.Web] Harvard CS50 and CS75
- Harvard CS50x: Intro CS & Web (https://cs50.harvard.edu/x/2021/)
- Harvard CS50: Intro CS & Web (https://cs50.harvard.edu/college/2021/spring/)
- Harvard CS50: Web Programming with Python and JavaScript (https://cs50.harvard.edu/web/2020/, YouTube, YouTube)
- Harvard CS75: Building Dynamic Website by David J Malan (CS75.TV, YouTube)
- [Web] Deep Dive into Modern Web Development (https://fullstackopen.com/en/)
- [Web] https://javascript.info/
- [Web] (MDN) Mozilla Developer Network (https://developer.mozilla.org/en-US/docs/Learn)
- [CS.DB] Stanford CS145: Data Management and Data Systems (Course, YouTube, YouTube)
- [CS.DB] CMU 15-445/645: Database Systems
- [CS.DB] CMU 15-721: Advanced Database Systems (Spring 2020) (Course, YouTube)
- [SystemDesign] https://github.com/donnemartin/system-design-primer
- [SystemDesign] ByteByteGo Blog by Alex Xu (https://blog.bytebytego.com/)
- [MLD] Stanford CS329S: Machine Learning System Design, Spring 2021
- [DistSys] An Introduction to Distributed Systems (https://github.com/aphyr/distsys-class)
- [DistSys] Distributed Systems for Fun and Profit Book (http://book.mixu.net/distsys/index.html)
- [DS] 52 Week Curriculum for Data Science in 2021 by Terrence Shin
- [Stat] StatQuest (https://statquest.org/video-index/)
- [ML/DL/NLP/GNN/GDL/RL] YouTube ML Courses (https://github.com/dair-ai/ML-YouTube-Courses)
- [ML] Awesome ML Courses (https://github.com/luspr/awesome-ml-courses)
- [MLD] Machine Learning Systems Design (https://github.com/chiphuyen/machine-learning-systems-design)
- [MLD] Applied ML (https://github.com/eugeneyan/applied-ml)
- [ML.DL.NLP] ML Surveys (https://github.com/eugeneyan/ml-surveys)
- [NLP] The NLP Pandect (https://github.com/ivan-bilan/The-NLP-Pandect)
- [SystemDesign] https://github.com/donnemartin/system-design-primer
- [DS.ML.Interview] Data Science Interviews
- [ML.Interview] 4 Types of Interview Questions for DS & ML
- [ML.DL.Code] Keras Code Examples (https://keras.io/examples/)
- [GraphNN] Must-Read Papers on Graph Neural Networks (https://github.com/thunlp/GNNPapers)
- [DL.Prod] Deep Learning in Production (https://github.com/The-AI-Summer/Deep-Learning-In-Production)
- [DS.ML] Python Data Science Handbook (https://jakevdp.github.io/PythonDataScienceHandbook/)
- [ML] Interpretable Machine Learning (https://christophm.github.io/interpretable-ml-book/)
- [ML] Probabilistic Programming and Bayesian Methods for Hackers by Davidson-Pilon (with PyMC3 and TFP)
- [ML] Bayesian Reasoning and Machine Learning by David Barber (BRML)
- [ML] Pattern Recognition and Machine Learning by Christopher Bishop (PRML)
- [ML] Probabilistic Machine Learning by Kevin Murphy (PML)
- [ML] Elements of Statistical Learning by Hastie, Tibshirani and Friedman (ESL)
- [ML] Introduction to Statistical Learning by James, Witten, Hastie and Tibshirani (ISLR)
- [ML/BigData] Mining of Massive Datasets by Leskovec, Rajaraman, Ullman (MMDS)
- [ML] Foundations of Data Science by Blum, Hopcroft, Kannan (FDS:pdf)
- [DL] Deep Learning Book by Goodfellow, Bengio and Courville (https://www.deeplearningbook.org/)
- [DL] Dive into Deep Learning by Zhang, Lipton, Li and Smola (https://d2l.ai/)
- [Graph/Network] Network Science Book by Barabási (http://networksciencebook.com/)
- [Grap/Network/GameTh] Networks, Crowds, and Markets by Easley and Kleinberg (http://www.cs.cornell.edu/home/kleinber/networks-book/)
- [Graph.Kernel] Graph Kernels: State-of-the-Art and Future Challenges (https://arxiv.org/abs/2011.03854)
- [GeomDL/Graph] Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges (https://arxiv.org/abs/2104.13478)
- [DL.GNN] Graph Representation Learning Book by Hamilton (https://www.cs.mcgill.ca/~wlh/grl_book/)
- [ML.MLE.MLD] Machine Learning Engineering by Andriy Burkov (http://www.mlebook.com/wiki/doku.php)
- [ML.MLE.MLD] Machine Learning Yearnings by Andrew Ng (Downloadable from https://www.deeplearning.ai/programs/)
- [ML] Approacing Almost Any Machine Learning Problem by Abhishek Thakur (https://github.com/abhishekkrthakur/approachingalmost)
- [DistSys] Distributed Systems for Fun and Profit Book (http://book.mixu.net/distsys/index.html)
- [SystemDesign] ByteByteGo Blog by Alex Xu (https://blog.bytebytego.com/)
- [NLP] NLP Overview (https://nlpoverview.com/)
- Lilian Weng's Blog (https://lilianweng.github.io/lil-log/)
- [DL] An Overview for Deep Learning for Curious People (https://lilianweng.github.io/lil-log/2017/06/21/an-overview-of-deep-learning.html)
- [DL] Predict Stock Prices Using RNN (https://lilianweng.github.io/lil-log/2017/07/08/predict-stock-prices-using-RNN-part-1.html and https://lilianweng.github.io/lil-log/2017/07/22/predict-stock-prices-using-RNN-part-2.html)
- [NLP] Learning Word Embeddings (https://lilianweng.github.io/lil-log/2017/10/15/learning-word-embedding.html)
- [RL] A Peek into Reinforcement Learning (https://lilianweng.github.io/lil-log/2018/02/19/a-long-peek-into-reinforcement-learning.html)
- [NLP] Attention (https://lilianweng.github.io/lil-log/2018/06/24/attention-attention.html)
- [NLP] Generalized Language Models (https://lilianweng.github.io/lil-log/2019/01/31/generalized-language-models.html)
- [AI] Evolution Strategies (https://lilianweng.github.io/lil-log/2019/09/05/evolution-strategies.html)
- [NLP] Transformer Family (https://lilianweng.github.io/lil-log/2020/04/07/the-transformer-family.html)
- [NLP] Open-Domain Question Answering System (https://lilianweng.github.io/lil-log/2020/10/29/open-domain-question-answering.html)
- Andrej Karpathy's Blog (http://karpathy.github.io/)
- [DL] Hacker's Guide to Neural Networks (http://karpathy.github.io/neuralnets/)
- [DL] A Recipe for Training Neural Networks (http://karpathy.github.io/2019/04/25/recipe/)
- [DL] The Unreasonable Effectiveness of RNNs (http://karpathy.github.io/2015/05/21/rnn-effectiveness/)
- [PhD] A Survival Guide to a PhD (http://karpathy.github.io/2016/09/07/phd/)
- Christopher Colah's Blog (http://colah.github.io/)
- [DL] Understanding LSTM Networks (http://colah.github.io/posts/2015-08-Understanding-LSTMs/)
- [DL] Attention and Augmented RNNs (https://distill.pub/2016/augmented-rnns/)
- [NLP] Deep Learning, NLP, Representations (http://colah.github.io/posts/2014-07-NLP-RNNs-Representations/)
- [DL] Neural Networks, Manifolds, Topology (http://colah.github.io/posts/2014-03-NN-Manifolds-Topology/)
- [DL] Neural Networks and Functional Programming (http://colah.github.io/posts/2015-09-NN-Types-FP/)
- [DL] Understanding Convolutions (http://colah.github.io/posts/2014-07-Understanding-Convolutions/)
- [DL] Group Convolutions (http://colah.github.io/posts/2014-12-Groups-Convolution/)
- [Info] Visual Information Theory (http://colah.github.io/posts/2015-09-Visual-Information/)
- [PhD] Do I Need to Go to University? (http://colah.github.io/posts/2020-05-University/)
- [NLP] Sebastian Ruder's Blog (https://ruder.io/)
- [ML] Sebastian Raschka's Blog (https://sebastianraschka.com/blog/)
- [DL] A Short Chronology of Deep Learning for Tabular Data (https://sebastianraschka.com/blog/2022/deep-learning-for-tabular-data.html)
- [DL] Understanding GRU Networks
- [ML.Interview] 4 Types of Interview Questions for DS & ML
- [ML] Feature Engineering Deep Diving: Binning & Encoding
- [NLP] Understanding BERT Transformer: Attention isn't all you need
- [NLP] Some Examples of Applying BERT in Specific Domain
- [NLP] Berkeley Neural Parser (https://github.com/nikitakit/self-attentive-parser)
- [NLP.Address] AddressNet: Robust Street Address Parser
- Netflix Tech Blog (https://netflixtechblog.com)
- Facebook Blog
- Engineering @FB (https://engineering.fb.com)
- ML Applications @FB (https://engineering.fb.com/category/ml-applications/)
- [How ML Powers FB's News Feed Ranking Algorithm
- Self-supervised Learning
- [ML] Elvis's Blog (https://elvissaravia.substack.com/archive)
- [ML.NLP.DL] Eugene Yan's Blog (https://eugeneyan.com/)
- [ML] On RecSys (https://eugeneyan.com/tag/recsys/)
- [ML] RecSys 2020 - Takeaways and Notable Papers (https://eugeneyan.com/writing/recsys2020/)
- [Ld] On Leadership (https://eugeneyan.com/tag/leadership/)
- [ML.GraphNN] Theoretical Foundations of Graph Neural Networks by Petar Veličković on YouTube
- [GraphML] GML in-depth: three forms of self-supervised learning (https://graphml.substack.com/p/self-supervised-learning)
- [GeoDL,GraphDL] Geometric Deep Learning - paper, blog, keynotes, lectures (https://geometricdeeplearning.com/)
- [GraphDL] Introducton to Graph Deep Learning and Where It May Be Heading
- [GraphML] How to Get Started with Graph Machine Learning
- [SystemDesign] (Tiktok's Recommendation System) Monolith: Real Time Recommendation System with Collisionless Embedding Table (https://arxiv.org/abs/2209.07663)